Efficiency Prediction System And Method For Rotating Device Using Transformation Of Learning data

摘要

The present invention relates to a system for predicting efficiency of a rotating body using transformation of learning data, comprising: a sensing unit obtaining an output load of a real-time input load of the rotating body; A calculation unit calculating a point-by-time efficiency of the rotating body based on the information obtained by the sensing unit; A processing unit for processing the efficiency of each point of view calculated by the calculating unit into image data in the form of coordinates; A transformation unit converting the image data in the form of coordinates into training data; A learning unit learning the learning data converted by the conversion unit through a deep learning technique; And an efficiency map modeling unit modeling an efficiency map obtained by accumulating the efficiency of each point of view of the rotating body based on the data learned through the learning unit. Characterized in that it comprises a. In addition, the present invention relates to a method for predicting the efficiency of a rotating body using the transformation of the training data, the first step of obtaining an output load for the real-time input load of the rotating body; A second step of calculating a point-in-time efficiency of the rotating body based on the information obtained from the first step; A third step of processing the point-by-view efficiency of the rotating body calculated through the second step into imaged data in the form of coordinates; A fourth step of converting the data processed in the third step into learning data; A fifth step of learning the learning data converted through the fourth step through a deep learning technique; And a sixth step of modeling an efficiency map obtained by accumulating the efficiency of each point of view of the rotating body based on the data learned through the fifth step. Characterized in that it comprises a. As a result, the limited actual measurement data of the rotating body is converted into learning data through various data conversion methods, and the deep learning is performed. The reliability of the overall efficiency prediction can be improved.